Machine Learning approaches in Lattice QCD - An interdisciplinary exchange

Session

Symmetry equivariant neural networks/informed neural networks

talks and panel discussion

Mar 2, 2023, 2:30 PM

Institute for Advanced Study of the Technische Universität München

Conveners

Symmetry equivariant neural networks/informed neural networks

• Phiala Shanahan ()

Description

Talks and panel discussion

Contribution list Timetable

93. Generation of gauge field configurations with equivariant neural networks

Matteo Favoni

3/2/23, 2:30 PM

95. TBA

Daniel Hackett

3/2/23, 2:50 PM

96. Panel discussion: 1. Symmetry-equivariance vs computational brute force 2. Computational challenges of gauge equivariance

Chair: Phiala Shanahan, Members: Gurtej Kanwar, Christoph Lehner, Matteo Favoni

3/2/23, 3:05 PM

• There is ongoing debate in the ML community about the value of trying to incorporate domain knowledge into architectures vs using computational brute force. What guides your intuition for the value of building symmetry-equivariant architectures? In your experience when is symmetry-equivariance valuable and when is it not?
• What makes gauge equivariance in particular challenging from a...

94. On gauge equivariant neural networks and adversarial attacks

Daniel Schuh